© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 99185
    Prev
    Next
    INDEX
    Explanations

    scientific research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    为主ä½ĵ
    -0.25
    çĽ¸ä¿¡
    -0.24
    Seat
    -0.24
    åºĶèģĺ
    -0.23
    ç´§åĩij
    -0.23
    op
    -0.23
    追éļı
    -0.23
     licensors
    -0.22
     retain
    -0.22
    èĢģé¾Ħ
    -0.22
    POSITIVE LOGITS
    umba
    0.28
    uhe
    0.24
    coe
    0.24
    -Fi
    0.24
    ivor
    0.24
     Oasis
    0.24
    ertools
    0.23
    æįº
    0.23
     coron
    0.23
    ouch
    0.23
    Activations Density 0.051%

    No Known Activations